© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21352
    Prev
    Next
    INDEX
    Explanations

    dates and days of the week

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åIJĦæł·
    -0.10
    äºĨèµ·æĿ¥
    -0.10
    lessly
    -0.10
    gether
    -0.10
    就好åĥı
    -0.09
    yled
    -0.09
    /from
    -0.09
    ently
    -0.09
    ãģªãĤĬ
    -0.09
    è´»
    -0.09
    POSITIVE LOGITS
    kel
    0.10
    maf
    0.09
    æĹ¥ä¸ĬåįĪ
    0.09
    ivar
    0.09
    sites
    0.09
    slow
    0.09
     occasion
    0.09
    æĹ¥ä¸ĭåįĪ
    0.08
    æľīçļĦ
    0.08
    æŁIJäºĽ
    0.08
    Activations Density 0.028%

    No Known Activations